我正在尝试使用keras调谐器来调整LSTM神经网络,以使用kaggle数据集来检测一篇文章是否为假新闻。/engine/input_spec.py", line 223, in assert_input_compatibilityValueError: Input/engine/input_spec.py", line 223, in assert_input_compatibility
str(tuple(shape)))
为什么下面的代码会提供ValueError: Input 0 is incompatible with layer dense_14: expected min_ndim=2, found ndim=1当我删除unroll=True时,它会起作用,这个参数不会影响LSTM的输出维度。from keras.models import Sequentialmodel = Sequential()
model.addfrom k
我一直在我的LSTM层中收到这个错误。ValueError: Error when checking input: expected lstm_input to have 3 dimensions, but got array with shapeself.data.shape) self.model = Sequential()
self.model.add(LSTM